Commit
•
79d0941
1
Parent(s):
e7c745d
Training in progress, step 34068
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +9 -3
- pytorch_model.bin +1 -1
- runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6319689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6446efa47ad7e736efdde8483d6b75decb0be4618886e2432c5c866015fa42ba
|
3 |
size 6319689
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c813a318f44fac110ab9a4b866cb85c71916828eb161b5be32af908e27827056
|
3 |
size 1121737121
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7273394cbc9be140ab287f7ad2eaade6d2b972c1aac199eca35bde1947f5fa92
|
3 |
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b928b49e9c102ca016aa13910d98920650bd0f2b04b51ce90356aeb8534bd4
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3141811a723dbaca8ba6eeb71a97ead093c6c130b024ef5da3343fd876364800
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -216,11 +216,17 @@
|
|
216 |
"learning_rate": 1.2362263976197919e-05,
|
217 |
"loss": 1.5005,
|
218 |
"step": 33000
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
}
|
220 |
],
|
221 |
"max_steps": 86379,
|
222 |
"num_train_epochs": 1,
|
223 |
-
"total_flos": 6.
|
224 |
"trial_name": null,
|
225 |
"trial_params": null
|
226 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.39440141701107906,
|
5 |
+
"global_step": 34068,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
216 |
"learning_rate": 1.2362263976197919e-05,
|
217 |
"loss": 1.5005,
|
218 |
"step": 33000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.39,
|
222 |
+
"learning_rate": 1.213095775593605e-05,
|
223 |
+
"loss": 1.5089,
|
224 |
+
"step": 34000
|
225 |
}
|
226 |
],
|
227 |
"max_steps": 86379,
|
228 |
"num_train_epochs": 1,
|
229 |
+
"total_flos": 6.344299026107597e+16,
|
230 |
"trial_name": null,
|
231 |
"trial_params": null
|
232 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1121737121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c813a318f44fac110ab9a4b866cb85c71916828eb161b5be32af908e27827056
|
3 |
size 1121737121
|
runs/Jun04_13-23-35_1c0366a2fd20/events.out.tfevents.1685885434.1c0366a2fd20.848.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a58e4e1dc9221ce9cef6cbc288eff56334ce5c23b50bcd0af333e97751a22fec
|
3 |
+
size 5949
|